{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NJ2KMHGYZW55L3ZE76TEVCJKRK","short_pith_number":"pith:NJ2KMHGY","canonical_record":{"source":{"id":"2604.18751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:55:04Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"dd9f079e63370cb5205f08f30d30c37bdf41157e669d60d085f325f74cf06a90","abstract_canon_sha256":"180bdd44da24a97cf42c53775a783c08bec9025a6dca7b6e530953742af37ce2"},"schema_version":"1.0"},"canonical_sha256":"6a74a61cd8cdbbd5ef24ffa64a892a8a952e67aea77d08fc51f9923fecfb8a64","source":{"kind":"arxiv","id":"2604.18751","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18751","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18751v1","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18751","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"NJ2KMHGYZW55","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"NJ2KMHGYZW55L3ZE","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"NJ2KMHGY","created_at":"2026-05-27T01:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NJ2KMHGYZW55L3ZE76TEVCJKRK","target":"record","payload":{"canonical_record":{"source":{"id":"2604.18751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:55:04Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"dd9f079e63370cb5205f08f30d30c37bdf41157e669d60d085f325f74cf06a90","abstract_canon_sha256":"180bdd44da24a97cf42c53775a783c08bec9025a6dca7b6e530953742af37ce2"},"schema_version":"1.0"},"canonical_sha256":"6a74a61cd8cdbbd5ef24ffa64a892a8a952e67aea77d08fc51f9923fecfb8a64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:58.115151Z","signature_b64":"h8owQH3aYAeejToVlJxyWworbAquhkYWOtLqphioLw/5YX6+oJpVwUe/A8d6AD8O5AAVhW9QGQiINHQs144CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a74a61cd8cdbbd5ef24ffa64a892a8a952e67aea77d08fc51f9923fecfb8a64","last_reissued_at":"2026-05-27T01:04:58.114637Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:58.114637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.18751","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RbZEyq72Nct7HpfGrKVxiiZgzv6YY48BgeuQOG1lacwzAEK58ngSFN0LMoAimBKdamcidYdMPIPIPLxh009TAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:14:44.190895Z"},"content_sha256":"0798c840af0f3847d5323ebcaab3fac6355d55e9d31be1b22f52ededf0870918","schema_version":"1.0","event_id":"sha256:0798c840af0f3847d5323ebcaab3fac6355d55e9d31be1b22f52ededf0870918"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NJ2KMHGYZW55L3ZE76TEVCJKRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size.","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dmitry Zaytsev, Michael Coppedge, Valentina Kuskova","submitted_at":"2026-04-20T18:55:04Z","abstract_excerpt":"Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In particular, causal scores produced by regularized neural autoregressive models are often treated as analogues of regression coefficients, leading to misleading claims of statistical significance.\n  In this paper, we argue that causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that systematic edge ablation combined with forecast comparison reliably identifies whether a candidate causal relationship is required for accurate prediction, without the ablation process itself introducing artifacts or biases","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Causal relevance in nonlinear time-series models is better assessed via forecast necessity through edge ablation and prediction comparison than via coefficient magnitudes, as illustrated on democracy panel data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9dbd47899d7261cd35da4c0058f059b492b2e34379df49d15347a531bb4c3631"},"source":{"id":"2604.18751","kind":"arxiv","version":1},"verdict":{"id":"cd8b5254-88fc-43c2-adbf-49ec743779c7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T05:50:03.455727Z","strongest_claim":"causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so","one_line_summary":"Causal relevance in nonlinear time-series models is better assessed via forecast necessity through edge ablation and prediction comparison than via coefficient magnitudes, as illustrated on democracy panel data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that systematic edge ablation combined with forecast comparison reliably identifies whether a candidate causal relationship is required for accurate prediction, without the ablation process itself introducing artifacts or biases","pith_extraction_headline":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18751/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T03:43:33.054346Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5205c90acbce16e2a7c9c4d02134dac29793a21b0ec9cd2650066f391b83d444"},"references":{"count":6,"sample":[{"doi":"","year":2022,"title":"Albini, E., Long, J., Dervovic, D., & Magazzeni, D. (2022). Counterfactual shapley additive explanations. In Proceed- ings of the 2022 ACM conference on fairness, accountabil- ity, and transparency (p","work_id":"de11d61a-2d75-4827-a442-5959dffe983a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Coppedge, M., Gerring, J., Knutsen, C.H., McMann, K., Mechkova, V ., Medzihorsky, J., Natsika, N., Neundorf, A., Paxton, P., Pemstein, D., von R ¨omer, J., Seim, B., Sigman, R., Skaaning, S.-E., Stato","work_id":"cc30d205-1bdd-4354-8eaf-2b3fd4bdf70a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Job, S., Tao, X., Cai, T., Xie, H., Li, L., Li, Q., & Yong, J. (2025). Exploring Causal Learning Through Graph Neu- ral Networks: An In-Depth Review. Wiley Interdisciplinary Reviews: Data Mining and K","work_id":"a3f05eaa-8d8c-472a-9ef4-8c99932f9912","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Lim, N., d’Alch´e-Buc, F., Auliac, C., & Michailidis, G. (2015). Operator-valued kernel-based vector autoregressive models for network inference. Machine Learning, 99(3), 489–513. Mehdiyev, N., Enke, ","work_id":"58f60cf8-5ed7-43b6-959f-ddcc32ab5c3c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"D., & Cooch, E","work_id":"26e579a7-6bcf-4b37-989d-b33fd09a8be0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":6,"snapshot_sha256":"8148941c780e17e55e8cc3888a54dfe9f09f9ce7dae6fc4f2cfc16c85b1e69a3","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cd8b5254-88fc-43c2-adbf-49ec743779c7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Caj2KDe0L9BsqZrHE39lqAshCKXvLb6i6xRZOW+qrXoRabITwVV9a6O2T36FOcFG3XdkG7d3zJ3wYfRonaDhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:14:44.191539Z"},"content_sha256":"cd19241478ff305cc484f5548c3899d3d6e686691380a555e4f3435e77437eb2","schema_version":"1.0","event_id":"sha256:cd19241478ff305cc484f5548c3899d3d6e686691380a555e4f3435e77437eb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/bundle.json","state_url":"https://pith.science/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-06T14:14:44Z","links":{"resolver":"https://pith.science/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK","bundle":"https://pith.science/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/bundle.json","state":"https://pith.science/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJ2KMHGYZW55L3ZE76TEVCJKRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NJ2KMHGYZW55L3ZE76TEVCJKRK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"180bdd44da24a97cf42c53775a783c08bec9025a6dca7b6e530953742af37ce2","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:55:04Z","title_canon_sha256":"dd9f079e63370cb5205f08f30d30c37bdf41157e669d60d085f325f74cf06a90"},"schema_version":"1.0","source":{"id":"2604.18751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18751","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18751v1","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18751","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"NJ2KMHGYZW55","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"NJ2KMHGYZW55L3ZE","created_at":"2026-05-27T01:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"NJ2KMHGY","created_at":"2026-05-27T01:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:cd19241478ff305cc484f5548c3899d3d6e686691380a555e4f3435e77437eb2","target":"graph","created_at":"2026-05-27T01:04:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"that systematic edge ablation combined with forecast comparison reliably identifies whether a candidate causal relationship is required for accurate prediction, without the ablation process itself introducing artifacts or biases"},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Causal relevance in nonlinear time-series models is better assessed via forecast necessity through edge ablation and prediction comparison than via coefficient magnitudes, as illustrated on democracy panel data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size."}],"snapshot_sha256":"9dbd47899d7261cd35da4c0058f059b492b2e34379df49d15347a531bb4c3631"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T03:43:33.054346Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.18751/integrity.json","findings":[],"snapshot_sha256":"5205c90acbce16e2a7c9c4d02134dac29793a21b0ec9cd2650066f391b83d444","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In particular, causal scores produced by regularized neural autoregressive models are often treated as analogues of regression coefficients, leading to misleading claims of statistical significance.\n  In this paper, we argue that causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so. ","authors_text":"Dmitry Zaytsev, Michael Coppedge, Valentina Kuskova","cross_cats":["cs.AI","stat.ME","stat.ML"],"headline":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:55:04Z","title":"Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models"},"references":{"count":6,"internal_anchors":0,"resolved_work":6,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Albini, E., Long, J., Dervovic, D., & Magazzeni, D. (2022). Counterfactual shapley additive explanations. In Proceed- ings of the 2022 ACM conference on fairness, accountabil- ity, and transparency (p","work_id":"de11d61a-2d75-4827-a442-5959dffe983a","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Coppedge, M., Gerring, J., Knutsen, C.H., McMann, K., Mechkova, V ., Medzihorsky, J., Natsika, N., Neundorf, A., Paxton, P., Pemstein, D., von R ¨omer, J., Seim, B., Sigman, R., Skaaning, S.-E., Stato","work_id":"cc30d205-1bdd-4354-8eaf-2b3fd4bdf70a","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Job, S., Tao, X., Cai, T., Xie, H., Li, L., Li, Q., & Yong, J. (2025). Exploring Causal Learning Through Graph Neu- ral Networks: An In-Depth Review. Wiley Interdisciplinary Reviews: Data Mining and K","work_id":"a3f05eaa-8d8c-472a-9ef4-8c99932f9912","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Lim, N., d’Alch´e-Buc, F., Auliac, C., & Michailidis, G. (2015). Operator-valued kernel-based vector autoregressive models for network inference. Machine Learning, 99(3), 489–513. Mehdiyev, N., Enke, ","work_id":"58f60cf8-5ed7-43b6-959f-ddcc32ab5c3c","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"D., & Cooch, E","work_id":"26e579a7-6bcf-4b37-989d-b33fd09a8be0","year":2025}],"snapshot_sha256":"8148941c780e17e55e8cc3888a54dfe9f09f9ce7dae6fc4f2cfc16c85b1e69a3"},"source":{"id":"2604.18751","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-10T05:50:03.455727Z","id":"cd8b5254-88fc-43c2-adbf-49ec743779c7","model_set":{"reader":"grok-4.3"},"one_line_summary":"Causal relevance in nonlinear time-series models is better assessed via forecast necessity through edge ablation and prediction comparison than via coefficient magnitudes, as illustrated on democracy panel data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Causal relevance in nonlinear time-series models is better judged by whether a link is required for accurate forecasts than by coefficient size.","strongest_claim":"causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so","weakest_assumption":"that systematic edge ablation combined with forecast comparison reliably identifies whether a candidate causal relationship is required for accurate prediction, without the ablation process itself introducing artifacts or biases"}},"verdict_id":"cd8b5254-88fc-43c2-adbf-49ec743779c7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0798c840af0f3847d5323ebcaab3fac6355d55e9d31be1b22f52ededf0870918","target":"record","created_at":"2026-05-27T01:04:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"180bdd44da24a97cf42c53775a783c08bec9025a6dca7b6e530953742af37ce2","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:55:04Z","title_canon_sha256":"dd9f079e63370cb5205f08f30d30c37bdf41157e669d60d085f325f74cf06a90"},"schema_version":"1.0","source":{"id":"2604.18751","kind":"arxiv","version":1}},"canonical_sha256":"6a74a61cd8cdbbd5ef24ffa64a892a8a952e67aea77d08fc51f9923fecfb8a64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a74a61cd8cdbbd5ef24ffa64a892a8a952e67aea77d08fc51f9923fecfb8a64","first_computed_at":"2026-05-27T01:04:58.114637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:58.114637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h8owQH3aYAeejToVlJxyWworbAquhkYWOtLqphioLw/5YX6+oJpVwUe/A8d6AD8O5AAVhW9QGQiINHQs144CAw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:58.115151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.18751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0798c840af0f3847d5323ebcaab3fac6355d55e9d31be1b22f52ededf0870918","sha256:cd19241478ff305cc484f5548c3899d3d6e686691380a555e4f3435e77437eb2"],"state_sha256":"6961533e238dcd659c253d8387a80e6773039d9bccc10e8cb011edcf1ab44c10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDNjcbZbrfs1XtDfSsilW4AzeQmQhOU9ZpWrXfP/PYR947HbgvJ9I2j2V5leQXh0m4J1ZpeKsv2ZDMpyy9h/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T14:14:44.194185Z","bundle_sha256":"536daddb3d93f149305b75169569f657d068c7a54c416e2337bbab78acfa36ca"}}